mlsanityData to 14 Oct 2026

LogicGaze: Benchmarking Causal Consistency in Visual Narratives via Counterfactual Verification

arXiv 2602.00292 ↗First posted 30 Jan 2026cs.CV cs.AIcited by 0

On the map: LLM reasoning → Hallucination detection and mitigation

also in 1 more
Abstract (arXiv)

While sequential reasoning enhances the capability of Vision-Language Models (VLMs) to execute complex multimodal tasks, their reliability in grounding these reasoning chains within actual visual evidence remains insufficiently explored. We introduce LogicGaze, a novel benchmark framework designed to rigorously interrogate whether VLMs can validate sequential causal chains against visual inputs, specifically targeting the pervasive issue of hallucination. Curated from 40,000 video segments from ShareGPT4Video and a subset of Flickr30k imagery, LogicGaze integrates causal sequences with visually contradictory yet linguistically plausible perturbations, compelling models to verify the authenticity of each reasoning step. Our tripartite evaluation protocol - Causal Validation, Grounded Narrative Synthesis, and Perturbation Rejection - exposes significant vulnerabilities in state-of-the-art VLMs such as Qwen2.5-VL-72B. LogicGaze advocates for robust, trustworthy multimodal reasoning, with all resources publicly available in an anonymized repository.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Hallucination detection and mitigation, one of 17 directions in LLM reasoning. Builds on 18 of its 21 references that are in the map. First posted on arXiv 30 Jan 2026.

Builds on

18 of 21 references.

References · 18

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2024Qwen2.5 Technical Reportcited by 4,942
  4. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  5. 2024RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMscited by 202
  6. 2024RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generationcited by 147
  7. 2024Inference Scaling for Long-Context Retrieval Augmented Generationcited by 65
  8. 2025CF-VLM:CounterFactual Vision-Language Fine-tuningcited by 59
  9. 2025GAM-Agent: Game-Theoretic and Uncertainty-Aware Collaboration for Complex Visual Reasoningcited by 58
  10. 2025KABB: Knowledge-Aware Bayesian Bandits for Dynamic Expert Coordination in Multi-Agent Systemscited by 37
  11. 2025MAT-Agent: Adaptive Multi-Agent Training Optimizationcited by 35
  12. 2025MM-CoT:A Benchmark for Probing Visual Chain-of-Thought Reasoning in Multimodal Modelscited by 34
6 more
  1. 2023SAIL: Search-Augmented Instruction Learningcited by 33
  2. 2025OSC: Cognitive Orchestration through Dynamic Knowledge Alignment in Multi-Agent LLM Collaborationcited by 30
  3. 2024AutoRAG: Automated Framework for optimization of Retrieval Augmented Generation Pipelinecited by 27
  4. 2025Hybrid Token Compression for Vision-Language Modelscited by 20
  5. 2025Kolmogorov-Arnold Fourier Networkscited by 18
  6. 2026Why Keep Your Doubts to Yourself? Trading Visual Uncertainties in Multi-Agent Bandit Systemscited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026HIVE: Understanding Post-Hallucination Reasoning in Vision Language Models
  2. 2026CDH-Bench: A Commonsense-Driven Hallucination Benchmark for Evaluating Visual Fidelity in Vision-Language Models
  3. 2025Treble Counterfactual VLMs: A Causal Approach to Hallucination
  4. 2026Vision-Language Introspection: Mitigating Overconfident Hallucinations in MLLMs via Interpretable Bi-Causal Steering
  5. 2025SegSub: Evaluating Robustness to Knowledge Conflicts and Hallucinations in Vision-Language Models
  6. 2026PVFH-Bench: Benchmarking Premise-Induced Visual Fixation Hallucinations in Vision-Language Models
  7. 2025Causal-LLaVA: Causal Disentanglement for Mitigating Hallucination in Multimodal Large Language Models
  8. 2025Generate, but Verify: Reducing Hallucination in Vision-Language Models with Retrospective Resampling